Machine Learning in Detecting COVID-19 Misinformation on Twitter

Implications of the health information pollution for society, health professionals, and science

In the era of ultra-connectivity, the proliferation of speculative notions driven by personal emotions eclipses the credibility of scientific evidence. This trend has led to an alarming surge in information pollution, particularly by the pervasive influence of social media platforms. Consequently, this overflow of falsehoods poses a significant threat to public health and overall societal well-being. In this sense, this critical review aims to present the harmful impacts of the health information pollution on society, health professionals, and health science, as well as strategies for their mitigation. The management of information pollution requires coordinated efforts to develop and implement multiple effective preventive and debunking strategies, such as the regulation of big tech companies' actions and algorithm data transparency, the education of health professionals on responsible social media use, and the establishment of a novel academic culture, shifting from the valorization of productivism to socially relevant scientific production. By acknowledging the complexities of this contemporary issue and drawing insights from distinct perspectives, it is possible to safeguard the integrity of information dissemination and foster a more informed and resilient community.

Dissecting the infodemic: An in-depth analysis of COVID-19 misinformation detection on X (formerly Twitter) utilizing machine learning and deep learning techniques

The alarming growth of misinformation on social media has become a global concern as it influences public opinions and compromises social, political, and public health development. The proliferation of deceptive information has resulted in widespread confusion, societal disturbances, and significant consequences for matters pertaining to health. Throughout the COVID-19 pandemic, there was a substantial surge in the dissemination of inaccurate or deceptive information via social media platforms, particularly X (formerly known as Twitter), resulting in the phenomenon commonly referred to as an "Infodemic". This review paper examines a grand selection of 600 articles published in the past five years and focuses on conducting a thorough analysis of 87 studies that investigate the detection of fake news connected to COVID-19 on Twitter. In addition, this research explores the algorithmic techniques and methodologies used to investigate the individuals responsible for disseminating this type of fake news. A summary of common datasets, along with their fundamental qualities, for detecting fake news has been included as well. For the purpose of identifying fake news, the behavioral pattern of the misinformation spreaders, and their community analysis, we have performed an in-depth examination of the most recent literature that the researchers have worked with and recommended. Our key findings can be summarized in a few points: (a) around 80% of fake news detection-related papers have utilized Deep Neural Networks-based techniques for better performance achievement, although the proposed models suffer from overfitting, vanishing gradients, and higher prediction time problems, (b) around 60% of the disseminator related analysis papers focus on identifying dominant spreaders and their communities utilizing graph modeling although there is not much work done in this domain, and finally, (c) we conclude by pointing out a wide range of research gaps, for example, the need of a large and robust training dataset and deeper investigation of the communities, etc., and suggesting potential solution strategies. Moreover, to facilitate the utilization of a large training dataset for detecting fake news, we have created a large database by compiling the training datasets from 17 different research works. The objective of this study is to shed light on exactly how COVID-19-related tweets are beginning to diverge, along with the dissemination of misinformation. Our work uncovers notable discoveries, including the ongoing rapid growth of the disseminator population, the presence of professional spreaders within the disseminator community, and a substantial level of collaboration among the fake news spreaders.

What is the impact of artificial intelligence-based chatbots on infodemic management?

Artificial intelligence (AI) chatbots have the potential to revolutionize online health information-seeking behavior by delivering up-to-date information on a wide range of health topics. They generate personalized responses to user queries through their ability to process extensive amounts of text, analyze trends, and generate natural language responses. Chatbots can manage infodemic by debunking online health misinformation on a large scale. Nevertheless, system accuracy remains technically challenging. Chatbots require training on diverse and representative datasets, security to protect against malicious actors, and updates to keep up-to-date on scientific progress. Therefore, although AI chatbots hold significant potential in assisting infodemic management, it is essential to approach their outputs with caution due to their current limitations.

Perception of COVID-19 vaccination among Indian Twitter users: computational approach

Vaccination has been a hot topic in the present COVID-19 context. The government, public health stakeholders and media are all concerned about how to get the people vaccinated. The study was intended to explore the perception and emotions of the Indians citizens toward COVID-19 vaccine from Twitter messages. The tweets were collected for the period of 6 months, from mid-January to June, 2021 using hash-tags and keywords specific to India. Topics and emotions from the tweets were extracted using Latent Dirichlet Allocation (LDA) method and National Research Council (NRC) Lexicon, respectively. Theme, sentiment and emotion wise engagement and reachability metrics were assessed. Hash-tag frequency of COVID-19 vaccine brands were also identified and evaluated. Information regarding 'Co-WIN app and availability of vaccine' was widely discussed and also received highest engagement and reachability among Twitter users. Among the various emotions, trust was expressed the most, which highlights the acceptance of vaccines among the Indian citizens. The hash-tags frequency of vaccine brands shows that Covishield was popular in the month of March 2021, and Covaxin in April 2021. The results from the study will help stakeholders to efficiently use social media to disseminate COVID-19 vaccine information on popular concerns. This in turn will encourage citizens to be vaccinated and achieve herd immunity. Similar methodology can be adopted in future to understand the perceptions and concerns of people in emergency situations.

Supplementary Information

The online version contains supplementary material available at 10.1007/s42001-023-00203-0.

Detecting and classifying online health misinformation with 'Content Similarity Measure (CSM)' algorithm: an automated fact-checking-based approach

Information dissemination occurs through the 'word of media' in the digital world. Fraudulent and deceitful content, such as misinformation, has detrimental effects on people. An implicit fact-based automated fact-checking technique comprising information retrieval, natural language processing, and machine learning techniques assist in assessing the credibility of content and detecting misinformation. Previous studies focused on linguistic and textual features and similarity measures-based approaches. However, these studies need to gain knowledge of facts, and similarity measures are less accurate when dealing with sparse or zero data. To fill these gaps, we propose a 'Content Similarity Measure (CSM)' algorithm that can perform automated fact-checking of URLs in the healthcare domain. Authors have introduced a novel set of content similarity, domain-specific, and sentiment polarity score features to achieve journalistic fact-checking. An extensive analysis of the proposed algorithm compared with standard similarity measures and machine learning classifiers showed that the 'content similarity score' feature outperformed other features with an accuracy of 88.26%. In the algorithmic approach, CSM showed improved accuracy of 91.06% compared to the Jaccard similarity measure with 74.26% accuracy. Another observation is that the algorithmic approach outperformed the feature-based method. To check the robustness of the algorithms, authors have tested the model on three state-of-the-art datasets, viz. CoAID, FakeHealth, and ReCOVery. With the algorithmic approach, CSM showed the highest accuracy of 87.30%, 89.30%, 85.26%, and 88.83% on CoAID, ReCOVery, FakeHealth (Story), and FakeHealth (Release) datasets, respectively. With a feature-based approach, the proposed CSM showed the highest accuracy of 85.93%, 87.97%, 83.92%, and 86.80%, respectively.

Ethical principles for infodemiology and infoveillance studies concerning infodemic management on social media

Big data originating from user interactions on social media play an essential role in infodemiology and infoveillance outcomes, supporting the planning and implementation of public health actions. Notably, the extrapolation of these data requires an awareness of different ethical elements. Previous studies have investigated and discussed the adoption of conventional ethical approaches in the contemporary public health digital surveillance space. However, there is a lack of specific ethical guidelines to orient infodemiology and infoveillance studies concerning infodemic on social media, making it challenging to design digital strategies to combat this phenomenon. Hence, it is necessary to explore if traditional ethical pillars can support digital purposes or whether new ones must be proposed since we are confronted with a complex online misinformation scenario. Therefore, this perspective provides an overview of the current scenario of ethics-related issues of infodemiology and infoveillance on social media for infodemic studies.

Fake or not? Automated detection of COVID-19 misinformation and disinformation in social networks and digital media

With the continuous spread of the COVID-19 pandemic, misinformation poses serious threats and concerns. COVID-19-related misinformation integrates a mixture of health aspects along with news and political misinformation. This mixture complicates the ability to judge whether a claim related to COVID-19 is information, misinformation, or disinformation. With no standard terminology in information and disinformation, integrating different datasets and using existing classification models can be impractical. To deal with these issues, we aggregated several COVID-19 misinformation datasets and compared differences between learning models from individual datasets versus one that was aggregated. We also evaluated the impact of using several word- and sentence-embedding models and transformers on the performance of classification models. We observed that whereas word-embedding models showed improvements in all evaluated classification models, the improvement level varied among the different classifiers. Although our work was focused on COVID-19 misinformation detection, a similar approach can be applied to myriad other topics, such as the recent Russian invasion of Ukraine.

Social media mining under the COVID-19 context: Progress, challenges, and opportunities

Social media platforms allow users worldwide to create and share information, forging vast sensing networks that allow information on certain topics to be collected, stored, mined, and analyzed in a rapid manner. During the COVID-19 pandemic, extensive social media mining efforts have been undertaken to tackle COVID-19 challenges from various perspectives. This review summarizes the progress of social media data mining studies in the COVID-19 contexts and categorizes them into six major domains, including early warning and detection, human mobility monitoring, communication and information conveying, public attitudes and emotions, infodemic and misinformation, and hatred and violence. We further document essential features of publicly available COVID-19 related social media data archives that will benefit research communities in conducting replicable and reproducible studies. In addition, we discuss seven challenges in social media analytics associated with their potential impacts on derived COVID-19 findings, followed by our visions for the possible paths forward in regard to social media-based COVID-19 investigations. This review serves as a valuable reference that recaps social media mining efforts in COVID-19 related studies and provides future directions along which the information harnessed from social media can be used to address public health emergencies.

Infodemic and fake news - A comprehensive overview of its global magnitude during the COVID-19 pandemic in 2021: A scoping review

The spread of fake news increased dramatically during the COVID-19 pandemic worldwide. This study aims to synthesize the extant literature to understand the magnitude of this phenomenon in the wake of the pandemic in 2021, focusing on the motives and sociodemographic profiles, Artificial Intelligence (AI)-based tools developed, and the top trending topics related to fake news. A scoping review was adopted targeting articles published in five academic databases (January 2021-November 2021), resulting in 97 papers. Most of the studies were empirical in nature (N = 69) targeting the general population (N = 26) and social media users (N = 13), followed by AI-based detection tools (N = 27). Top motives for fake news sharing include low awareness, knowledge, and health/media literacy, Entertainment/Pass Time/Socialization, Altruism, and low trust in government/news media, whilst the phenomenon was more prominent among those with low education, males and younger. Machine and deep learning emerged to be the widely explored techniques in detecting fake news, whereas top topics were related to vaccine, virus, cures/remedies, treatment, and prevention. Immediate intervention and prevention efforts are needed to curb this anti-social behavior considering the world is still struggling to contain the spread of the COVID-19 virus.

Effects of Pope Francis' Religious Authority and Media Coverage on Twitter User's Attitudes toward COVID-19 Vaccination

This paper is interdisciplinary and combines the research perspective of medical studies with that of media and social communication studies and theological studies. The main goal of this article is to determine [from arguments on all sides of the issue] whether, and to what extent, statements issued by a religious authority can be used as an argument in the COVID-19 vaccination campaign. The authors also want to find answers to the questions of how the pope's comments affect public opinion when they concern the sphere of secular and everyday life, including issues related to health care. The main method used in this study is desktop research and the analysis of the Roman Catholic Church's teaching on vaccination and on the types and significance of the pope's statements on various topics. The auxiliary methods are sentiment analysis and network analysis made in the open source software Gephi. The authors are strongly interested in the communication and media aspect of the analyzed situation. Pope Francis' voice on the COVID-19 vaccination has certainly been noticed and registered worldwide, but the effectiveness of his message and direct impact on Catholics' decisions to accept or refuse the COVID-19 vaccination is quite questionable and would require further precise research. Comparing this to the regularities known from political marketing, one would think that the pope's statement would not convince the firm opponents of vaccination.